Skip to content

feature: Djl Large Model Support #3628

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
Mar 6, 2023
Merged

feature: Djl Large Model Support #3628

merged 2 commits into from
Mar 6, 2023

Conversation

siddvenk
Copy link
Contributor

@siddvenk siddvenk commented Feb 2, 2023 •
edited
Loading

Issue #, if available:
Please wait to merge this PR until #3685 has been merged

Description of changes:
This change adds a new module, djl_inference, that provides Model implementations that leverage the djl_inference DLCs. We provide a Model implementations that let users leverage the different engines/backends we offer in our DJL DLCs.

This integration makes it easy for users to deploy large models that require multiple GPUs (via Tensor Parallelism or Pipeline Parallelism) on Sagemaker.

Testing done:

  • All model types for for both DeepSpeed integration, and HuggingFace Accelerate integration have been tested with an ml.g5.48xlarge endpoint instance. I can share more details and the notebook with the testing code if needed.
  • Tested cases where user supplies no code or configuration files, user supplies partial files, and user supplies all files and configuration either locally or via s3.
  • We might want to add some test cases to the integration test case suite, but I want to confirm this with the repo owners as the tests require gpu instances and we need to think through how we host the model artifacts for tests.

Merge Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.

General

  • I have read the CONTRIBUTING doc
  • I certify that the changes I am introducing will be backward compatible, and I have discussed concerns about this, if any, with the Python SDK team
  • I used the commit message format described in CONTRIBUTING
  • I have passed the region in to all S3 and STS clients that I've initialized as part of this change.
  • I have updated any necessary documentation, including READMEs and API docs (if appropriate)

Tests

  • I have added tests that prove my fix is effective or that my feature works (if appropriate)
  • I have added unit and/or integration tests as appropriate to ensure backward compatibility of the changes
  • I have checked that my tests are not configured for a specific region or account (if appropriate)
  • I have used unique_name_from_base to create resource names in integ tests (if appropriate)

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: 886bb82
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: 886bb82
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: 886bb82
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: 886bb82
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: 886bb82
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: de58b21
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: de58b21
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: de58b21
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: de58b21
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: de58b21
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: c068bad
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: c068bad
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: c068bad
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: c068bad
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: c068bad
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@siddvenk siddvenk force-pushed the djl-llm-models branch 2 times, most recently from 6f72f65 to 802ac5b Compare February 10, 2023 23:57
@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: 51b989f
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: ae0177b
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: bba5929
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: bba5929
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: bba5929
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: bba5929
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: bba5929
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: f17f059
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: f17f059
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: f17f059
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: f03307c
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: f03307c
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: f03307c
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: f03307c
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: f03307c
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: 467e829
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

frankfliu
frankfliu reviewed Mar 3, 2023
View reviewed changes
doc/frameworks/djl/using_djl.rst Outdated
djl_model = DJLModel(
"s3://my_bucket/my_saved_model_artifacts/",
"my_sagemaker_role",
djl_version="0.21.0",
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should remove this line in example. Use latest version is recommended way

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will remove djl_version from the example snippets

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@siddvenk
Copy link
Contributor Author

siddvenk commented Mar 4, 2023

@knikure

We have reviewed the docs here with our PM and they are ok to proceed. I have 2 approvals from my team, and the dependent PR #3685 has been merged.

Are we good to merge this PR now?

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: 226c5f6
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@knikure knikure removed the do-not-merge Use when PR needs to be marked as do not merge label Mar 6, 2023
knikure
knikure reviewed Mar 6, 2023
View reviewed changes
Copy link
Contributor

@knikure knikure left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

/bot run slow-tests

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: 226c5f6
  • Result: FAILED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@knikure knikure changed the title [feature]: Djl Large Model Support feature: Djl Large Model Support Mar 6, 2023
@knikure knikure merged commit 16f5a68 into aws:master Mar 6, 2023
@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-local-mode-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-notebook-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-pr
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-slow-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: sagemaker-python-sdk-unit-tests
  • Commit ID: 226c5f6
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@siddvenk siddvenk deleted the djl-llm-models branch March 9, 2023 21:34
nmadan pushed a commit to nmadan/sagemaker-python-sdk that referenced this pull request Apr 18, 2023
@siddvenk
feature: Djl Large Model Support (aws#3628)
8c98424
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@rohithkrn rohithkrn rohithkrn left review comments

@frankfliu frankfliu frankfliu approved these changes

@knikure knikure knikure left review comments

@lanking520 lanking520 lanking520 approved these changes

Assignees

@knikure knikure

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@siddvenk @sagemaker-bot @codecov-commenter @rohithkrn @lanking520 @frankfliu @knikure